Diagnosis of Coronary Artery Disease Using Artificial Intelligence Based Decision Support System

Heart disease is any disease that affects the normal condition and functionality of heart.
Coronary Artery Disease (CAD) is the most common. It is caused by the accumulation of
plaques within the walls of the coronary arteries that supply blood to the heart muscles. It
may lead to continued temporary oxygen deprivation that will result in the damage of
heart muscles. CAD caused more than 7,000,000 deaths every year in the worldwide. It is
the second cause of death in Malaysia and the major cause of death in the world. To
diagnose CAD, cardiologists usually perform many diagnostic steps. Unfortunately, the
results of the diagnostic tests are difficult to interpret which do not always provide
defmite answer, but may lead to different opinion. To help cardiologists providing correct
diagnosis of CAD in less expensive and non- invasive manner, many researchers had
developed decision support system to diagnose CAD.
A fuzzy decision support system for the diagnosis of coronary artery disease based on
rough set theory is proposed in this thesis. The objective is to develop an evidence based
fuzzy decision support system for the diagnosis of coronary artery disease. This proposed
system is based on evidences or raw medical data sets, which are taken from University
California Irvine (UCI) database. The proposed system is designed to be able to handle
the uncertainty, incompleteness and heterogeneity of data sets. Artificial Neural Network
with Rough Set Theory attribute reduction (ANNRST) is proposed is the imputation
method to solve the incompleteness of data sets. Evaluations of ANNRST based on
classifiers performance and rule filtering are proposed by comparing ANNRST and other
methods using classifiers and during rule filtering process. RST rule inq'u ction is applied
to ANNRST imputed data sets. Numerical values are discretized using Boolean reasoning
method. Rule selection based on quality and importance is proposed. RST rule
importance measure is used to select the most important high quality rules. The selected
rules are used to build fuzzy decision support systems. Fuzzification based on
discretization cuts and fuzzy rule weighing based on rule quality are proposed. Mamdani
inference method is used to provide the decision with centroid defuziification to give
numerical results, which represent the possibility of blocking in coronary, arteries.
The results show that proposed ANNRST has similar performance to ANN and
outperforms k-Nearest Neighbour (k-NN) and Concept Most Common attribute valueFilling (CMCF). ANNRST is simpler than ANN because it has fewer input attributes and
more suitable to be applied for missing data imputation problem. ANNRST also provides
strong relationship between original and imputed data sets. It is shown that ANNRST
provide better RST rule based classifier than CMCF and k-NN during rule filtering
process. Proposed RST based rule selection also performs better than other filtering
methods. Developed Fuzzy Decision Support System (FOSS) provides better
performance compared to multi layer perceptron ANN, k-NN, rule induction method
called C4.5 and Repeated Incremental Pruning to Produce Error Reduction (RIPPER)
applied on UCI CAD data sets and Ipoh Specialist Hospital's patients. FOSS has
transparent knowledge representation, heterogeneous and incomplete input data handling
capability. FOSS is able to give the approximate percentage of blocking of coronary
artery based on 13 standard attributes based on historical, simple blood test and ECG
data, etc, where coronary angiography or cardiologist can not give the percentage. The
results of FOSS were evaluated by three local cardiologists and considered to be efficient
and useful.